{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MO3PJLQNZIMKIMVDYETUMQXUSR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"13e6daa40f373a7ec09b4e5102618e97f405b3defb55771bc884f7c8adfbccd7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:48:11Z","title_canon_sha256":"a3ede3702392427c3142e0e950ab68f5e19b7b54882848bd0420b184e23974d8"},"schema_version":"1.0","source":{"id":"2505.18044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18044","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18044v1","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18044","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_12","alias_value":"MO3PJLQNZIMK","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_16","alias_value":"MO3PJLQNZIMKIMVD","created_at":"2026-07-05T11:08:35Z"},{"alias_kind":"pith_short_8","alias_value":"MO3PJLQN","created_at":"2026-07-05T11:08:35Z"}],"graph_snapshots":[{"event_id":"sha256:190d18e2e04847e2f01c37f8ba175d9d5943ab4b9a9aa316a96d2f1e63d908d7","target":"graph","created_at":"2026-07-05T11:08:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.18044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many real-world decision-making problems face the off-dynamics challenge: the agent learns a policy in a source domain and deploys it in a target domain with different state transitions. The distributionally robust Markov decision process (DRMDP) addresses this challenge by finding a robust policy that performs well under the worst-case environment within a pre-specified uncertainty set of transition dynamics. Its effectiveness heavily hinges on the proper design of these uncertainty sets, based on prior knowledge of the dynamics. In this work, we propose a novel linear mixture DRMDP framework","authors_text":"Pan Xu, Zhishuai Liu","cross_cats":["cs.AI","cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:48:11Z","title":"Linear Mixture Distributionally Robust Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18044","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7d24f59c0278d7f254147af5f43dfb05d2dc81fc85fe767f5aa75435514c4763","target":"record","created_at":"2026-07-05T11:08:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"13e6daa40f373a7ec09b4e5102618e97f405b3defb55771bc884f7c8adfbccd7","cross_cats_sorted":["cs.AI","cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-23T15:48:11Z","title_canon_sha256":"a3ede3702392427c3142e0e950ab68f5e19b7b54882848bd0420b184e23974d8"},"schema_version":"1.0","source":{"id":"2505.18044","kind":"arxiv","version":1}},"canonical_sha256":"63b6f4ae0dca18a432a3c1274642f4944e40adaa1eb9e49041494511eafd9699","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"63b6f4ae0dca18a432a3c1274642f4944e40adaa1eb9e49041494511eafd9699","first_computed_at":"2026-07-05T11:08:35.877918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:35.877918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i+0qH3ylOug4LGZXqbMHoiW/3EHTJoERKs3DE6UlPMbr8IOyMzK4qY8UiFdaiADoHYi8ISbaDQgLEIYb+hsyBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:35.878489Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d24f59c0278d7f254147af5f43dfb05d2dc81fc85fe767f5aa75435514c4763","sha256:190d18e2e04847e2f01c37f8ba175d9d5943ab4b9a9aa316a96d2f1e63d908d7"],"state_sha256":"c7070518a30bd4b291257bb39ba44ae19988d6c8a48b3c1bc6cfb12042babd6e"}